goallisted

# Shape a goal A goal is a pointer, not a plan. The computer board owns priority, entity pointers, claims, owners, and resume. The entity's committed `PLAN.md` owns the outcome, decisions, checkpoints, acceptance, proof, and anti-sprawl controls. ## Compile 1. Read the board, owning plan, active claims, Git state, and named surfaces. 2. If the plan is not executable, update it with the missing authority, contradictions, acceptance, and reachable checkpoints, then continue into implementation. Stop after planning only when explicitly asked. 3. Emit at most 80 words, normally three one-line sentences: ```text Outcome: <finite end state and what the person stops supervising>. Resume: <refreshed board + PLAN.md at committed ref>; continue owned claims, then the highest-value reachable checkpoint. Proof: <mechanical finish line>; keep source, merge, install/deploy, and live distinct. ``` Never copy inventories, skill or agent rosters, implementation sequences, test matrices, capability routing, anti-sprawl lists, or unrelated prohibitions into the launcher. Do not add `Authority`, `Scope`, `Policy`, or `Method` lines when standing policy and `PLAN.md` already answer them. Add one extra line only for a request-specific prohibition or human boundary. Put new durable detail in `PLAN.md` and point to it. A broad outcome stays broad; brevity must not narrow it to one task. For a loose steer, translate only the operative signal using [amplify](./references/amplify.md). ## Q